遗忘用户认知记忆

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the destructiveHint annotation, the description discloses critical behavioral detail: degrade preserves the evidence chain and halves confidence, while delete is permanent and unrecoverable. This gives the agent essential awareness of side effects and irreversibility, which annotations alone do not fully convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, front-loaded with the core action, and logically organized with Args and Returns sections. Every line adds value, and there is no filler or redundant elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even without an output schema, the description explicitly specifies the return shape: { success: boolean, mode: string }. It also covers both modes, their side effects, default behavior, and the optional reason parameter. This is sufficient for an agent to invoke the tool correctly and understand the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents all parameters with 100% coverage, so the baseline is 3. The description adds meaningful behavioral semantics, particularly that degrade halves confidence and delete is irreversible, going beyond the schema's enum descriptions. The Args section also clearly marks reason as optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's core action: '删除或降级一条用户记忆' (delete or degrade a user memory). It further specifies two distinct modes with concrete semantics, making it easily distinguishable from sibling tools like cognitive_search, cognitive_write, and cognitive_update.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear situational guidance: degrade is recommended when '用户想法变了' (the user's thoughts changed), while delete is for complete removal and marked as irreversible. It does not explicitly mention alternative sibling tools for non-destructive updates, but the mode-selection guidance is clear enough for most use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.